基于形态学滤波和小角度边缘搜索的运动自适应去隔行

Motion Adaptive De-interlacing Based on Mathematical Morphology Filtering and Low Angle Edge Detection

为实现隔行扫描到逐行扫描的视频格式转换,提出了一种运动自适应的去隔行算法,主要包括运动估计、运动向量的形态学滤波、小角度边缘搜索、时空插值权重自适应插值等。该算法通过同极性场的像素块绝对值差和(SAD)与运动阈值的比较实现运动估计,并对运动向量进行形态学滤波处理,消除噪声影响。在小角度边缘搜索中采用自适应搜索半径和并行搜索树的策略实现最小6°的检测精度。最后,通过时空权重自适应的插值算法实现去隔行处理,取得了很好的处理效果。

The function of de-interlace is to convert interlaced images to progressive ones. In this paper, a motion adaptive de-interlacing algorithm based on edge direction is presented. It consists of motion estimation, low-angle edge detection, and spatio-temporal weight adaptive interpolation. It estimates the motion by comparing the sum of absolute block difference （SAD） between same-parity fields with the threshold of motion. The motion information obtained by motion estimation is filtered by a mathematical morphology filter. The low-angle edge detection uses an adaptive searching radius and parallel search strategy in which the 6° edge can be detected. Experimental results show that the proposed method achieves high image quality with low hardware complexity.